Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/omrikais/cctally/reportgit clone --depth 1 https://github.com/omrikais/cctallyWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02119 |
| Opus 5 | $0.00000 | $0.01059 |
| Sonnet 5 | $0.00000 | $0.00424 |
| Haiku 4.5 | $0.00000 | $0.00212 |
Grade A, and why
report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
report
Trend table of dollars per 1% weekly usage. The headline command of this project.
Claude cost coverage: Claude dollar and token totals are transcript-derived lower bounds, not exact
/usagebilling totals. Codex accounting is unaffected.
Provider-aware report routing
cctally report and cctally report --source claude preserve the existing
Claude subscription-week trend. The flat command also accepts --source {claude,codex,all} (default claude); cctally claude report and cctally codex report are fixed-source forms and do not accept --source.
Codex report is quota-window-native, not a calendar or Claude subscription
week report. It emits one source/root/logical-limit series, using each selected
native reset block's [reset - window, min(as-of, reset)) accounting interval.
The --weeks N value selects the newest N S2 reset blocks within every logical
limit series, including the current block. Cost per percent is null/unavailable
when the selected percent or quota/cost evidence is insufficient; it is never
fabricated as zero.
--source all keeps Claude subscription-week rows and every Codex logical-limit
series in separate source sections. It has no combined trend, average,
USD, token total, used percent, reset, or dollars-per-percent field: one Codex
accounting interval can overlap multiple logical limits, so adding per-limit
series would double count physical usage. That refusal is specifically about
overlapping logical-limit series, not about combining providers as such:
the dashboard does publish a combined USD figure over one shared absolute range
for its cross-provider rankings, which carry no per-limit series to overlap. --speed applies to Codex/all;
--week-start-name, --mode, --offline, and --project are Claude-only
options (they affect only the Claude leg of all); --detail remains
source-native in both sections.
The fixed cctally codex report parser accepts only its native surface: it
does not expose the Claude-only --week-start-name, --mode, --offline, or
--project flags. Its --sync-current syncs Codex accounting and reconciles
native quota state; it does not invoke sync-week.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 151 lines · 0 tokens per session scan A b3041a56b047
report is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,119 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.